schuetoliver
/
handson-ml
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Make font sizes consistent across notebooks

main
Aurélien Geron 2021-11-27 23:03:26 +13:00
parent e72b210d97
commit 52d4f0a8c6
9 changed files with 141 additions and 156 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
01_the_machine_learning_landscape.ipynb
View File

@ -93,7 +93,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"To plot pretty figures directly within Jupyter:" "Let's define the default font sizes, to plot pretty figures:"
] ]
}, },
{ {
@ -104,8 +104,11 @@
"source": [ "source": [
"import matplotlib.pyplot as plt\n", "import matplotlib.pyplot as plt\n",
"\n", "\n",
"plt.rc('font', size=12)\n", "plt.rc('font', size=14)\n",
"plt.rc('axes', labelsize=14)" "plt.rc('axes', labelsize=14, titlesize=14)\n",
"plt.rc('legend', fontsize=14)\n",
"plt.rc('xtick',labelsize=10)\n",
"plt.rc('ytick',labelsize=10)"
] ]
}, },
{ {
@ -403,11 +406,12 @@
"max_life_sat = 9\n", "max_life_sat = 9\n",
"\n", "\n",
"position_text = {\n", "position_text = {\n",
" \"Hungary\": (28_000, 4.2),\n", " \"Turkey\": (29_500, 4.2),\n",
" \"Hungary\": (28_000, 6.9),\n",
" \"France\": (40_000, 5),\n", " \"France\": (40_000, 5),\n",
" \"New Zealand\": (28_000, 8.2),\n", " \"New Zealand\": (28_000, 8.2),\n",
" \"Australia\": (50_000, 5.5),\n", " \"Australia\": (50_000, 5.5),\n",
" \"United States\": (59_000, 5.5),\n", " \"United States\": (59_000, 5.3),\n",
" \"Denmark\": (46_000, 8.5)\n", " \"Denmark\": (46_000, 8.5)\n",
"}\n", "}\n",
"\n", "\n",
@ -416,7 +420,7 @@
" pos_data_y = country_stats[lifesat_col].loc[country]\n", " pos_data_y = country_stats[lifesat_col].loc[country]\n",
" country = \"U.S.\" if country == \"United States\" else country\n", " country = \"U.S.\" if country == \"United States\" else country\n",
" plt.annotate(country, xy=(pos_data_x, pos_data_y),\n", " plt.annotate(country, xy=(pos_data_x, pos_data_y),\n",
" xytext=pos_text,\n", " xytext=pos_text, fontsize=12,\n",
" arrowprops=dict(facecolor='black', width=0.5,\n", " arrowprops=dict(facecolor='black', width=0.5,\n",
" shrink=0.15, headwidth=5))\n", " shrink=0.15, headwidth=5))\n",
" plt.plot(pos_data_x, pos_data_y, \"ro\")\n", " plt.plot(pos_data_x, pos_data_y, \"ro\")\n",
@ -499,9 +503,9 @@
"X = np.linspace(min_gdp, max_gdp, 1000)\n", "X = np.linspace(min_gdp, max_gdp, 1000)\n",
"plt.plot(X, t0 + t1 * X, \"b\")\n", "plt.plot(X, t0 + t1 * X, \"b\")\n",
"\n", "\n",
"plt.text(max_gdp - 20_000, min_life_sat + 1.5,\n", "plt.text(max_gdp - 20_000, min_life_sat + 1.9,\n",
" fr\"$\\theta_0 = {t0:.2f}$\", color=\"b\")\n", " fr\"$\\theta_0 = {t0:.2f}$\", color=\"b\")\n",
"plt.text(max_gdp - 20_000, min_life_sat + 1,\n", "plt.text(max_gdp - 20_000, min_life_sat + 1.3,\n",
" fr\"$\\theta_1 = {t1 * 1e5:.2f} \\times 10^{{-5}}$\", color=\"b\")\n", " fr\"$\\theta_1 = {t1 * 1e5:.2f} \\times 10^{{-5}}$\", color=\"b\")\n",
"\n", "\n",
"plt.axis([min_gdp, max_gdp, min_life_sat, max_life_sat])\n", "plt.axis([min_gdp, max_gdp, min_life_sat, max_life_sat])\n",
@ -542,9 +546,9 @@
"X = np.linspace(min_gdp, max_gdp, 1000)\n", "X = np.linspace(min_gdp, max_gdp, 1000)\n",
"plt.plot(X, t0 + t1 * X, \"b\")\n", "plt.plot(X, t0 + t1 * X, \"b\")\n",
"\n", "\n",
"plt.text(min_gdp + 15_000, max_life_sat - 1.5,\n", "plt.text(min_gdp + 22_000, max_life_sat - 1.1,\n",
" fr\"$\\theta_0 = {t0:.2f}$\", color=\"b\")\n", " fr\"$\\theta_0 = {t0:.2f}$\", color=\"b\")\n",
"plt.text(min_gdp + 15_000, max_life_sat - 1,\n", "plt.text(min_gdp + 22_000, max_life_sat - 0.6,\n",
" fr\"$\\theta_1 = {t1 * 1e5:.2f} \\times 10^{{-5}}$\", color=\"b\")\n", " fr\"$\\theta_1 = {t1 * 1e5:.2f} \\times 10^{{-5}}$\", color=\"b\")\n",
"\n", "\n",
"plt.plot([cyprus_gdp_per_capita, cyprus_gdp_per_capita],\n", "plt.plot([cyprus_gdp_per_capita, cyprus_gdp_per_capita],\n",
@ -600,7 +604,7 @@
"for country, pos_text in position_text_missing_countries.items():\n", "for country, pos_text in position_text_missing_countries.items():\n",
" pos_data_x, pos_data_y = missing_data.loc[country]\n", " pos_data_x, pos_data_y = missing_data.loc[country]\n",
" plt.annotate(country, xy=(pos_data_x, pos_data_y),\n", " plt.annotate(country, xy=(pos_data_x, pos_data_y),\n",
" xytext=pos_text,\n", " xytext=pos_text, fontsize=12,\n",
" arrowprops=dict(facecolor='black', width=0.5,\n", " arrowprops=dict(facecolor='black', width=0.5,\n",
" shrink=0.1, headwidth=5))\n", " shrink=0.1, headwidth=5))\n",
" plt.plot(pos_data_x, pos_data_y, \"rs\")\n", " plt.plot(pos_data_x, pos_data_y, \"rs\")\n",
@ -694,7 +698,7 @@
"t0ridge, t1ridge = ridge.intercept_[0], ridge.coef_[0][0]\n", "t0ridge, t1ridge = ridge.intercept_[0], ridge.coef_[0][0]\n",
"plt.plot(X, t0ridge + t1ridge * X, \"b--\",\n", "plt.plot(X, t0ridge + t1ridge * X, \"b--\",\n",
" label=\"Regularized linear model on partial data\")\n", " label=\"Regularized linear model on partial data\")\n",
"plt.legend(loc=\"lower right\")\n", "plt.legend(loc=\"lower right\", fontsize=13)\n",
"\n", "\n",
"plt.axis([0, 115_000, min_life_sat, max_life_sat])\n", "plt.axis([0, 115_000, min_life_sat, max_life_sat])\n",
"\n", "\n",

2
02_end_to_end_machine_learning_project.ipynb
View File

@ -198,7 +198,7 @@
"import matplotlib.pyplot as plt\n", "import matplotlib.pyplot as plt\n",
"\n", "\n",
"# not in the book – the next 5 lines define the default font sizes\n", "# not in the book – the next 5 lines define the default font sizes\n",
"plt.rc('font', size=12)\n", "plt.rc('font', size=14)\n",
"plt.rc('axes', labelsize=14, titlesize=14)\n", "plt.rc('axes', labelsize=14, titlesize=14)\n",
"plt.rc('legend', fontsize=14)\n", "plt.rc('legend', fontsize=14)\n",
"plt.rc('xtick',labelsize=10)\n", "plt.rc('xtick',labelsize=10)\n",

185
03_classification.ipynb
View File

@ -86,7 +86,7 @@
"source": [ "source": [
"import matplotlib.pyplot as plt\n", "import matplotlib.pyplot as plt\n",
"\n", "\n",
"plt.rc('font', size=12)\n", "plt.rc('font', size=14)\n",
"plt.rc('axes', labelsize=14, titlesize=14)\n", "plt.rc('axes', labelsize=14, titlesize=14)\n",
"plt.rc('legend', fontsize=14)\n", "plt.rc('legend', fontsize=14)\n",
"plt.rc('xtick',labelsize=10)\n", "plt.rc('xtick',labelsize=10)\n",
@ -689,7 +689,7 @@
"plt.ylabel('True Positive Rate (Recall)')\n", "plt.ylabel('True Positive Rate (Recall)')\n",
"plt.grid()\n", "plt.grid()\n",
"plt.axis([0, 1, 0, 1])\n", "plt.axis([0, 1, 0, 1])\n",
"plt.legend(loc=\"lower right\")\n", "plt.legend(loc=\"lower right\", fontsize=13)\n",
"save_fig(\"roc_curve_plot\")\n", "save_fig(\"roc_curve_plot\")\n",
"\n", "\n",
"plt.show()" "plt.show()"
@ -1033,6 +1033,7 @@
"from sklearn.metrics import ConfusionMatrixDisplay\n", "from sklearn.metrics import ConfusionMatrixDisplay\n",
"\n", "\n",
"y_train_pred = cross_val_predict(sgd_clf, X_train_scaled, y_train, cv=3)\n", "y_train_pred = cross_val_predict(sgd_clf, X_train_scaled, y_train, cv=3)\n",
"plt.rc('font', size=9) # not in the book – make the text smaller\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred)\n", "ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred)\n",
"plt.show()" "plt.show()"
] ]
@ -1043,6 +1044,7 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"plt.rc('font', size=10) # not in the book\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred,\n", "ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred,\n",
" normalize=\"true\", values_format=\".0%\")\n", " normalize=\"true\", values_format=\".0%\")\n",
"plt.show()" "plt.show()"
@ -1055,6 +1057,7 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"sample_weight = (y_train_pred != y_train)\n", "sample_weight = (y_train_pred != y_train)\n",
"plt.rc('font', size=10) # not in the book\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred,\n", "ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred,\n",
" sample_weight=sample_weight,\n", " sample_weight=sample_weight,\n",
" normalize=\"true\", values_format=\".0%\")\n", " normalize=\"true\", values_format=\".0%\")\n",
@ -1076,8 +1079,10 @@
"source": [ "source": [
"# not in the book – this code generates Figure 3–9\n", "# not in the book – this code generates Figure 3–9\n",
"fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(9, 4))\n", "fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(9, 4))\n",
"plt.rc('font', size=9)\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred, ax=axs[0])\n", "ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred, ax=axs[0])\n",
"axs[0].set_title(\"Confusion matrix\")\n", "axs[0].set_title(\"Confusion matrix\")\n",
"plt.rc('font', size=10)\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred, ax=axs[1],\n", "ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred, ax=axs[1],\n",
" normalize=\"true\", values_format=\".0%\")\n", " normalize=\"true\", values_format=\".0%\")\n",
"axs[1].set_title(\"CM normalized by row\")\n", "axs[1].set_title(\"CM normalized by row\")\n",
@ -1093,6 +1098,7 @@
"source": [ "source": [
"# not in the book – this code generates Figure 3–10\n", "# not in the book – this code generates Figure 3–10\n",
"fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(9, 4))\n", "fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(9, 4))\n",
"plt.rc('font', size=10)\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred, ax=axs[0],\n", "ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred, ax=axs[0],\n",
" sample_weight=sample_weight,\n", " sample_weight=sample_weight,\n",
" normalize=\"true\", values_format=\".0%\")\n", " normalize=\"true\", values_format=\".0%\")\n",
@ -1102,7 +1108,8 @@
" normalize=\"pred\", values_format=\".0%\")\n", " normalize=\"pred\", values_format=\".0%\")\n",
"axs[1].set_title(\"Errors normalized by column\")\n", "axs[1].set_title(\"Errors normalized by column\")\n",
"save_fig(\"confusion_matrix_plot_2\")\n", "save_fig(\"confusion_matrix_plot_2\")\n",
"plt.show()" "plt.show()\n",
"plt.rc('font', size=14) # make fonts great again"
] ]
}, },
{ {
@ -1293,36 +1300,6 @@
"plt.show()" "plt.show()"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Extra Material — Calibrating Estimated Probabilities"
]
},
{
"cell_type": "code",
"execution_count": 89,
"metadata": {},
"outputs": [],
"source": [
"# TODO"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
@ -1353,7 +1330,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 90, "execution_count": 89,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1379,7 +1356,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 91, "execution_count": 90,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1394,7 +1371,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 92, "execution_count": 91,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1403,7 +1380,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 93, "execution_count": 92,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1419,7 +1396,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 94, "execution_count": 93,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1458,7 +1435,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 95, "execution_count": 94,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1467,7 +1444,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 96, "execution_count": 95,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1486,7 +1463,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 97, "execution_count": 96,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1519,7 +1496,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 98, "execution_count": 97,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1544,7 +1521,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 99, "execution_count": 98,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1562,7 +1539,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 100, "execution_count": 99,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1571,7 +1548,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 101, "execution_count": 100,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1587,7 +1564,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 102, "execution_count": 101,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1603,7 +1580,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 103, "execution_count": 102,
"metadata": { "metadata": {
"tags": [] "tags": []
}, },
@ -1643,7 +1620,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 104, "execution_count": 103,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1667,7 +1644,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 105, "execution_count": 104,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1690,7 +1667,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 106, "execution_count": 105,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1730,7 +1707,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 107, "execution_count": 106,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1747,7 +1724,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 108, "execution_count": 107,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1756,7 +1733,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 109, "execution_count": 108,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1786,7 +1763,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 110, "execution_count": 109,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1811,7 +1788,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 111, "execution_count": 110,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1827,7 +1804,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 112, "execution_count": 111,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1836,7 +1813,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 113, "execution_count": 112,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1845,7 +1822,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 114, "execution_count": 113,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1868,7 +1845,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 115, "execution_count": 114,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1890,7 +1867,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 116, "execution_count": 115,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1899,7 +1876,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 117, "execution_count": 116,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1919,7 +1896,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 118, "execution_count": 117,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1943,7 +1920,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 119, "execution_count": 118,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1960,7 +1937,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 120, "execution_count": 119,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1976,7 +1953,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 121, "execution_count": 120,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1993,7 +1970,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 122, "execution_count": 121,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2010,7 +1987,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 123, "execution_count": 122,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2034,7 +2011,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 124, "execution_count": 123,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2061,7 +2038,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 125, "execution_count": 124,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2095,7 +2072,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 126, "execution_count": 125,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2105,7 +2082,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 127, "execution_count": 126,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2139,7 +2116,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 128, "execution_count": 127,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2166,7 +2143,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 129, "execution_count": 128,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2182,7 +2159,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 130, "execution_count": 129,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2192,7 +2169,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 131, "execution_count": 130,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2201,7 +2178,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 132, "execution_count": 131,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2217,7 +2194,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 133, "execution_count": 132,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2231,7 +2208,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 134, "execution_count": 133,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2248,7 +2225,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 135, "execution_count": 134,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2257,7 +2234,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 136, "execution_count": 135,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2273,7 +2250,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 137, "execution_count": 136,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2291,7 +2268,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 138, "execution_count": 137,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2307,7 +2284,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 139, "execution_count": 138,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2316,7 +2293,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 140, "execution_count": 139,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2339,7 +2316,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 141, "execution_count": 140,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2356,7 +2333,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 142, "execution_count": 141,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2372,7 +2349,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 143, "execution_count": 142,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2395,7 +2372,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 144, "execution_count": 143,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2419,7 +2396,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 145, "execution_count": 144,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2438,7 +2415,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 146, "execution_count": 145,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2454,7 +2431,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 147, "execution_count": 146,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2478,7 +2455,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 148, "execution_count": 147,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2494,7 +2471,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 149, "execution_count": 148,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2515,7 +2492,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 150, "execution_count": 149,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2537,7 +2514,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 151, "execution_count": 150,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2558,7 +2535,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 152, "execution_count": 151,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2611,7 +2588,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 153, "execution_count": 152,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2636,7 +2613,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 154, "execution_count": 153,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2669,7 +2646,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 155, "execution_count": 154,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2680,7 +2657,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 156, "execution_count": 155,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2696,7 +2673,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 157, "execution_count": 156,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2712,7 +2689,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 158, "execution_count": 157,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2728,7 +2705,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 159, "execution_count": 158,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -2751,7 +2728,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 160, "execution_count": 159,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [

2
04_training_linear_models.ipynb
View File

@ -88,7 +88,7 @@
"source": [ "source": [
"import matplotlib.pyplot as plt\n", "import matplotlib.pyplot as plt\n",
"\n", "\n",
"plt.rc('font', size=12)\n", "plt.rc('font', size=14)\n",
"plt.rc('axes', labelsize=14, titlesize=14)\n", "plt.rc('axes', labelsize=14, titlesize=14)\n",
"plt.rc('legend', fontsize=14)\n", "plt.rc('legend', fontsize=14)\n",
"plt.rc('xtick',labelsize=10)\n", "plt.rc('xtick',labelsize=10)\n",

2
05_support_vector_machines.ipynb
View File

@ -88,7 +88,7 @@
"source": [ "source": [
"import matplotlib.pyplot as plt\n", "import matplotlib.pyplot as plt\n",
"\n", "\n",
"plt.rc('font', size=12)\n", "plt.rc('font', size=14)\n",
"plt.rc('axes', labelsize=14, titlesize=14)\n", "plt.rc('axes', labelsize=14, titlesize=14)\n",
"plt.rc('legend', fontsize=14)\n", "plt.rc('legend', fontsize=14)\n",
"plt.rc('xtick',labelsize=10)\n", "plt.rc('xtick',labelsize=10)\n",

2
06_decision_trees.ipynb
View File

@ -88,7 +88,7 @@
"source": [ "source": [
"import matplotlib.pyplot as plt\n", "import matplotlib.pyplot as plt\n",
"\n", "\n",
"plt.rc('font', size=12)\n", "plt.rc('font', size=14)\n",
"plt.rc('axes', labelsize=14, titlesize=14)\n", "plt.rc('axes', labelsize=14, titlesize=14)\n",
"plt.rc('legend', fontsize=14)\n", "plt.rc('legend', fontsize=14)\n",
"plt.rc('xtick',labelsize=10)\n", "plt.rc('xtick',labelsize=10)\n",

10
07_ensemble_learning_and_random_forests.ipynb
View File

@ -86,11 +86,13 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import matplotlib as mpl\n", "import matplotlib.pyplot as plt\n",
"\n", "\n",
"mpl.rc('font', size=12)\n", "plt.rc('font', size=14)\n",
"mpl.rc('axes', labelsize=14, titlesize=14)\n", "plt.rc('axes', labelsize=14, titlesize=14)\n",
"mpl.rc('legend', fontsize=14)" "plt.rc('legend', fontsize=14)\n",
"plt.rc('xtick',labelsize=10)\n",
"plt.rc('ytick',labelsize=10)"
] ]
}, },
{ {

40
08_dimensionality_reduction.ipynb
View File

@ -86,11 +86,13 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import matplotlib as mpl\n", "import matplotlib.pyplot as plt\n",
"\n", "\n",
"mpl.rc('font', size=12)\n", "plt.rc('font', size=14)\n",
"mpl.rc('axes', labelsize=14, titlesize=14)\n", "plt.rc('axes', labelsize=14, titlesize=14)\n",
"mpl.rc('legend', fontsize=14)" "plt.rc('legend', fontsize=14)\n",
"plt.rc('xtick',labelsize=10)\n",
"plt.rc('ytick',labelsize=10)"
] ]
}, },
{ {
@ -136,7 +138,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Let's generate a small 3D dataset:" "Let's generate a small 3D dataset. It's an oval shape, rotated in 3D space, with points distributed unevenly, and with quite a lot of noise:"
] ]
}, },
{ {
@ -145,19 +147,19 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# not in the book – we've generated plenty of datasets before with similar code\n", "# not in the book\n",
"\n", "\n",
"import numpy as np\n", "import numpy as np\n",
"from scipy.spatial.transform import Rotation\n",
"\n", "\n",
"np.random.seed(42)\n",
"m = 60\n", "m = 60\n",
"angles = (np.random.rand(m) ** 3 + 0.5) * 2 * np.pi\n", "X = np.zeros((m, 3)) # initialize 3D dataset\n",
"X = np.zeros((m, 3))\n", "np.random.seed(42)\n",
"X[:, 0] = np.cos(angles)\n", "angles = (np.random.rand(m) ** 3 + 0.5) * 2 * np.pi # uneven distribution\n",
"X[:, 1] = np.sin(angles) * 0.5\n", "X[:, 0], X[:, 1] = np.cos(angles), np.sin(angles) * 0.5 # oval\n",
"X += 0.28 * np.random.randn(m, 3)\n", "X += 0.28 * np.random.randn(m, 3) # add more noise\n",
"X = rotate_3d(X, -np.pi / 4, np.pi / 30, -np.pi / 20)\n", "X = Rotation.from_rotvec([np.pi / 29, -np.pi / 20, np.pi / 4]).apply(X)\n",
"X += [0.2, 0, 0.2]" "X += [0.2, 0, 0.2] # shift a bit"
] ]
}, },
{ {
@ -435,10 +437,8 @@
" length_includes_head=True, head_length=0.1, fc=\"b\", ec=\"b\", zorder=10)\n", " length_includes_head=True, head_length=0.1, fc=\"b\", ec=\"b\", zorder=10)\n",
"plt.arrow(0, 0, u3[0], u3[1], head_width=0.1, linewidth=1, alpha=0.9,\n", "plt.arrow(0, 0, u3[0], u3[1], head_width=0.1, linewidth=1, alpha=0.9,\n",
" length_includes_head=True, head_length=0.1, fc=\"b\", ec=\"b\", zorder=10)\n", " length_includes_head=True, head_length=0.1, fc=\"b\", ec=\"b\", zorder=10)\n",
"plt.text(u1[0] + 0.1, u1[1] - 0.05, r\"$\\mathbf{c_1}$\",\n", "plt.text(u1[0] + 0.1, u1[1] - 0.05, r\"$\\mathbf{c_1}$\", color=\"blue\")\n",
" color=\"blue\", fontsize=14)\n", "plt.text(u3[0] + 0.1, u3[1], r\"$\\mathbf{c_2}$\", color=\"blue\")\n",
"plt.text(u3[0] + 0.1, u3[1], r\"$\\mathbf{c_2}$\",\n",
" color=\"blue\", fontsize=14)\n",
"plt.xlabel(\"$x_1$\")\n", "plt.xlabel(\"$x_1$\")\n",
"plt.ylabel(\"$x_2$\", rotation=0)\n", "plt.ylabel(\"$x_2$\", rotation=0)\n",
"plt.axis([-1.4, 1.4, -1.4, 1.4])\n", "plt.axis([-1.4, 1.4, -1.4, 1.4])\n",
@ -1029,7 +1029,6 @@
"source": [ "source": [
"# not in the book – this cell generates and saves Figure 8–10\n", "# not in the book – this cell generates and saves Figure 8–10\n",
"\n", "\n",
"plt.title(\"Unrolled swiss roll using LLE\")\n",
"plt.scatter(X_unrolled[:, 0], X_unrolled[:, 1],\n", "plt.scatter(X_unrolled[:, 0], X_unrolled[:, 1],\n",
" c=t, cmap=darker_hot)\n", " c=t, cmap=darker_hot)\n",
"plt.xlabel(\"$z_1$\")\n", "plt.xlabel(\"$z_1$\")\n",
@ -1038,6 +1037,7 @@
"plt.grid(True)\n", "plt.grid(True)\n",
"\n", "\n",
"save_fig(\"lle_unrolling_plot\")\n", "save_fig(\"lle_unrolling_plot\")\n",
"plt.title(\"Unrolled swiss roll using LLE\")\n",
"plt.show()" "plt.show()"
] ]
}, },
@ -1826,7 +1826,7 @@
"\n", "\n",
"lda = LinearDiscriminantAnalysis(n_components=2)\n", "lda = LinearDiscriminantAnalysis(n_components=2)\n",
"%time X_lda_reduced = lda.fit_transform(X_sample, y_sample)\n", "%time X_lda_reduced = lda.fit_transform(X_sample, y_sample)\n",
"plot_digits(X_lda_reduced, y_sample, figsize=(12,12))\n", "plot_digits(X_lda_reduced, y_sample, figsize=(12, 12))\n",
"plt.show()" "plt.show()"
] ]
}, },

26
09_unsupervised_learning.ipynb
View File

@ -86,11 +86,13 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"import matplotlib as mpl\n", "import matplotlib.pyplot as plt\n",
"\n", "\n",
"mpl.rc('font', size=12)\n", "plt.rc('font', size=14)\n",
"mpl.rc('axes', labelsize=14, titlesize=14)\n", "plt.rc('axes', labelsize=14, titlesize=14)\n",
"mpl.rc('legend', fontsize=14)" "plt.rc('legend', fontsize=14)\n",
"plt.rc('xtick',labelsize=10)\n",
"plt.rc('ytick',labelsize=10)"
] ]
}, },
{ {
@ -1082,7 +1084,7 @@
"plt.ylabel(\"Inertia\")\n", "plt.ylabel(\"Inertia\")\n",
"plt.annotate(\"\", xy=(4, inertias[3]), xytext=(4.45, 650),\n", "plt.annotate(\"\", xy=(4, inertias[3]), xytext=(4.45, 650),\n",
" arrowprops=dict(facecolor='black', shrink=0.1))\n", " arrowprops=dict(facecolor='black', shrink=0.1))\n",
"plt.text(4.5, 650, \"Elbow\", fontsize=14, horizontalalignment=\"center\")\n", "plt.text(4.5, 650, \"Elbow\", horizontalalignment=\"center\")\n",
"plt.axis([1, 8.5, 0, 1300])\n", "plt.axis([1, 8.5, 0, 1300])\n",
"plt.grid()\n", "plt.grid()\n",
"save_fig(\"inertia_vs_k_plot\")\n", "save_fig(\"inertia_vs_k_plot\")\n",
@ -2410,9 +2412,9 @@
"plt.plot(stds[max_idx], max_val, \"r.\")\n", "plt.plot(stds[max_idx], max_val, \"r.\")\n",
"plt.plot([stds[max_idx], stds[max_idx]], [0, max_val], \"r:\")\n", "plt.plot([stds[max_idx], stds[max_idx]], [0, max_val], \"r:\")\n",
"plt.plot([0, stds[max_idx]], [max_val, max_val], \"r:\")\n", "plt.plot([0, stds[max_idx]], [max_val, max_val], \"r:\")\n",
"plt.text(stds[max_idx]+ 0.01, 0.081, r\"$\\hat{\\theta}$\", fontsize=14)\n", "plt.text(stds[max_idx]+ 0.01, 0.081, r\"$\\hat{\\theta}$\")\n",
"plt.text(stds[max_idx]+ 0.01, max_val - 0.005, r\"$Max$\", fontsize=14)\n", "plt.text(stds[max_idx]+ 0.01, max_val - 0.006, r\"$Max$\")\n",
"plt.text(1.01, max_val - 0.008, r\"$\\hat{\\mathcal{L}}$\", fontsize=14)\n", "plt.text(1.01, max_val - 0.008, r\"$\\hat{\\mathcal{L}}$\")\n",
"plt.ylabel(r\"$\\mathcal{L}$\", rotation=0, labelpad=10)\n", "plt.ylabel(r\"$\\mathcal{L}$\", rotation=0, labelpad=10)\n",
"plt.title(fr\"$\\mathcal{{L}}(\\theta|x={x_val}) = f(x={x_val}; \\theta)$\")\n", "plt.title(fr\"$\\mathcal{{L}}(\\theta|x={x_val}) = f(x={x_val}; \\theta)$\")\n",
"plt.grid()\n", "plt.grid()\n",
@ -2433,9 +2435,9 @@
"plt.plot(stds[log_max_idx], log_max_val, \"r.\")\n", "plt.plot(stds[log_max_idx], log_max_val, \"r.\")\n",
"plt.plot([stds[log_max_idx], stds[log_max_idx]], [-5, log_max_val], \"r:\")\n", "plt.plot([stds[log_max_idx], stds[log_max_idx]], [-5, log_max_val], \"r:\")\n",
"plt.plot([0, stds[log_max_idx]], [log_max_val, log_max_val], \"r:\")\n", "plt.plot([0, stds[log_max_idx]], [log_max_val, log_max_val], \"r:\")\n",
"plt.text(stds[log_max_idx]+ 0.01, log_max_val - 0.05, r\"$Max$\", fontsize=14)\n", "plt.text(stds[log_max_idx]+ 0.01, log_max_val - 0.06, r\"$Max$\")\n",
"plt.text(stds[log_max_idx]+ 0.01, -2.49, r\"$\\hat{\\theta}$\", fontsize=14)\n", "plt.text(stds[log_max_idx]+ 0.01, -2.49, r\"$\\hat{\\theta}$\")\n",
"plt.text(1.01, log_max_val - 0.07, r\"$\\log \\, \\hat{\\mathcal{L}}$\", fontsize=14)\n", "plt.text(1.01, log_max_val - 0.08, r\"$\\log \\, \\hat{\\mathcal{L}}$\")\n",
"plt.xlabel(r\"$\\theta$\")\n", "plt.xlabel(r\"$\\theta$\")\n",
"plt.ylabel(r\"$\\log\\mathcal{L}$\", rotation=0, labelpad=10)\n", "plt.ylabel(r\"$\\log\\mathcal{L}$\", rotation=0, labelpad=10)\n",
"plt.title(fr\"$\\log \\, \\mathcal{{L}}(\\theta|x={x_val})$\")\n", "plt.title(fr\"$\\log \\, \\mathcal{{L}}(\\theta|x={x_val})$\")\n",
@ -2527,7 +2529,7 @@
"plt.axis([1, 9.5, min(aics) - 50, max(aics) + 50])\n", "plt.axis([1, 9.5, min(aics) - 50, max(aics) + 50])\n",
"plt.annotate(\"\", xy=(3, bics[2]), xytext=(3.4, 8650),\n", "plt.annotate(\"\", xy=(3, bics[2]), xytext=(3.4, 8650),\n",
" arrowprops=dict(facecolor='black', shrink=0.1))\n", " arrowprops=dict(facecolor='black', shrink=0.1))\n",
"plt.text(3.5, 8660, \"Minimum\", fontsize=14, horizontalalignment=\"center\")\n", "plt.text(3.5, 8660, \"Minimum\", horizontalalignment=\"center\")\n",
"plt.legend()\n", "plt.legend()\n",
"plt.grid()\n", "plt.grid()\n",
"save_fig(\"aic_bic_vs_k_plot\")\n", "save_fig(\"aic_bic_vs_k_plot\")\n",